A Syntactic Skeleton for Statistical Machine Translation (2006)
| Venue: | In Proceedings of the 11th Conference of the European Association for Machine Translation |
| Citations: | 4 - 3 self |
BibTeX
@INPROCEEDINGS{Mellebeek06asyntactic,
author = {Bart Mellebeek and Karolina Owczarzak and Declan Groves and Josef Van Genabith and Andy Way},
title = {A Syntactic Skeleton for Statistical Machine Translation},
booktitle = {In Proceedings of the 11th Conference of the European Association for Machine Translation},
year = {2006},
pages = {195--202}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
We present a method for improving statistical machine translation performance by using linguistically motivated syntactic information. Our algorithm recursively decomposes source language sentences into syntactically simpler and shorter chunks, and recomposes their translation to form target language sentences. This improves both the word order and lexical selection of the translation. We report statistically significant relative improvements of 3.3 % BLEU score in an experiment (English→Spanish) carried out on an 800-sentence test set extracted from the Europarl corpus. 1
